franklei01

> Get the same case from my side. > > [@franklei01](https://github.com/franklei01) You mean by set below env macro to 1 before run llama-cli would get vulkan output correctly? GGML_VK_DISABLE_COOPMAT Yes,...

In this case, when building the mat mul [shaders](https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm.comp), some specialization constants (TM/TN/TK) are set to 0, and most of compute logic in mat mul are skipped. I think that's...